mirror of
https://github.com/unclecode/crawl4ai.git
synced 2026-06-11 16:28:11 +00:00
8995c1bbd6
The /crawl endpoint now accepts an optional crawler_configs field (list of CrawlerRunConfig dicts) alongside the existing crawler_config. When provided with multiple URLs, each config is deserialized and passed as a list to arun_many(), enabling per-URL configuration with url_matcher patterns. Single-URL requests and requests without crawler_configs are unchanged (backward compatible). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
115 lines
3.7 KiB
Python
115 lines
3.7 KiB
Python
from typing import List, Optional, Dict
|
||
from enum import Enum
|
||
from pydantic import BaseModel, Field, HttpUrl
|
||
from utils import FilterType
|
||
|
||
|
||
class CrawlRequest(BaseModel):
|
||
urls: List[str] = Field(min_length=1, max_length=100)
|
||
browser_config: Optional[Dict] = Field(default_factory=dict)
|
||
crawler_config: Optional[Dict] = Field(default_factory=dict)
|
||
crawler_configs: Optional[List[Dict]] = Field(
|
||
default=None,
|
||
description=(
|
||
"List of per-URL CrawlerRunConfig dicts for arun_many(). "
|
||
"When provided, each config can include a 'url_matcher' pattern "
|
||
"to match against specific URLs. Takes precedence over crawler_config."
|
||
),
|
||
)
|
||
|
||
|
||
class HookConfig(BaseModel):
|
||
"""Configuration for user-provided hooks"""
|
||
code: Dict[str, str] = Field(
|
||
default_factory=dict,
|
||
description="Map of hook points to Python code strings"
|
||
)
|
||
timeout: int = Field(
|
||
default=30,
|
||
ge=1,
|
||
le=120,
|
||
description="Timeout in seconds for each hook execution"
|
||
)
|
||
|
||
class Config:
|
||
schema_extra = {
|
||
"example": {
|
||
"code": {
|
||
"on_page_context_created": """
|
||
async def hook(page, context, **kwargs):
|
||
# Block images to speed up crawling
|
||
await context.route("**/*.{png,jpg,jpeg,gif}", lambda route: route.abort())
|
||
return page
|
||
""",
|
||
"before_retrieve_html": """
|
||
async def hook(page, context, **kwargs):
|
||
# Scroll to load lazy content
|
||
await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
|
||
await page.wait_for_timeout(2000)
|
||
return page
|
||
"""
|
||
},
|
||
"timeout": 30
|
||
}
|
||
}
|
||
|
||
|
||
class CrawlRequestWithHooks(CrawlRequest):
|
||
"""Extended crawl request with hooks support"""
|
||
hooks: Optional[HookConfig] = Field(
|
||
default=None,
|
||
description="Optional user-provided hook functions"
|
||
)
|
||
|
||
class MarkdownRequest(BaseModel):
|
||
"""Request body for the /md endpoint."""
|
||
url: str = Field(..., description="Absolute http/https URL to fetch")
|
||
f: FilterType = Field(FilterType.FIT, description="Content‑filter strategy: fit, raw, bm25, or llm")
|
||
q: Optional[str] = Field(None, description="Query string used by BM25/LLM filters")
|
||
c: Optional[str] = Field("0", description="Cache‑bust / revision counter")
|
||
provider: Optional[str] = Field(None, description="LLM provider override (e.g., 'anthropic/claude-3-opus')")
|
||
temperature: Optional[float] = Field(None, description="LLM temperature override (0.0-2.0)")
|
||
base_url: Optional[str] = Field(None, description="LLM API base URL override")
|
||
|
||
|
||
class RawCode(BaseModel):
|
||
code: str
|
||
|
||
class HTMLRequest(BaseModel):
|
||
url: str
|
||
|
||
class ScreenshotRequest(BaseModel):
|
||
url: str
|
||
screenshot_wait_for: Optional[float] = 2
|
||
wait_for_images: Optional[bool] = False
|
||
output_path: Optional[str] = None
|
||
|
||
class PDFRequest(BaseModel):
|
||
url: str
|
||
output_path: Optional[str] = None
|
||
|
||
|
||
class JSEndpointRequest(BaseModel):
|
||
url: str
|
||
scripts: List[str] = Field(
|
||
...,
|
||
description="List of separated JavaScript snippets to execute"
|
||
)
|
||
|
||
|
||
class WebhookConfig(BaseModel):
|
||
"""Configuration for webhook notifications."""
|
||
webhook_url: HttpUrl
|
||
webhook_data_in_payload: bool = False
|
||
webhook_headers: Optional[Dict[str, str]] = None
|
||
|
||
|
||
class WebhookPayload(BaseModel):
|
||
"""Payload sent to webhook endpoints."""
|
||
task_id: str
|
||
task_type: str # "crawl", "llm_extraction", etc.
|
||
status: str # "completed" or "failed"
|
||
timestamp: str # ISO 8601 format
|
||
urls: List[str]
|
||
error: Optional[str] = None
|
||
data: Optional[Dict] = None # Included only if webhook_data_in_payload=True |